Frequent rule reduction for phishing URL classification using fuzzy deep neural network model

Kumar, M. Sathish; Indrani, B.

doi:10.1007/s42044-020-00067-x

Cited by 8 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different parameters are used, but this is not a complete solution [ P21 ] Model for specific cases C4. Real-time phishing detection No solution [ P12 ] Model efficiency C5. Required too much computing resources No solution S2.…”

Section: Resultsmentioning

confidence: 99%

Applications of deep learning for phishing detection: a systematic literature review

Çatal

Giray²,

Tekinerdoğan

et al. 2022

Knowl Inf Syst

View full text Add to dashboard Cite

Phishing attacks aim to steal confidential information using sophisticated methods, techniques, and tools such as phishing through content injection, social engineering, online social networks, and mobile applications. To avoid and mitigate the risks of these attacks, several phishing detection approaches were developed, among which deep learning algorithms provided promising results. However, the results and the corresponding lessons learned are fragmented over many different studies and there is a lack of a systematic overview of the use of deep learning algorithms in phishing detection. Hence, we performed a systematic literature review (SLR) to identify, assess, and synthesize the results on deep learning approaches for phishing detection as reported by the selected scientific publications. We address nine research questions and provide an overview of how deep learning algorithms have been used for phishing detection from several aspects. In total, 43 journal articles were selected from electronic databases to derive the answers for the defined research questions. Our SLR study shows that except for one study, all the provided models applied supervised deep learning algorithms. The widely used data sources were URL-related data, third party information on the website, website content-related data, and email. The most used deep learning algorithms were deep neural networks (DNN), convolutional neural networks, and recurrent neural networks/long short-term memory networks. DNN and hybrid deep learning algorithms provided the best performance among other deep learning-based algorithms. 72% of the studies did not apply any feature selection algorithm to build the prediction model. PhishTank was the most used dataset among other datasets. While Keras and Tensorflow were the most preferred deep learning frameworks, 46% of the articles did not mention any framework. This study also highlights several challenges for phishing detection to pave the way for further research.

show abstract

Section: Resultsmentioning

confidence: 99%

Applications of deep learning for phishing detection: a systematic literature review

Çatal

Giray²,

Tekinerdoğan

et al. 2022

Knowl Inf Syst

View full text Add to dashboard Cite

show abstract

“…In order to replace the knowledge base of the expert system, Mahdavifar and Ghorbani (2020) developed a knowledge base by employing Deep Embedded Network Expert Systems (DeNNeS) to extract precise rules from a trained deep network (DNN) architecture [17]. By combining the best possible set of characteristics and criteria, Kumar and Indrani (2020) proposed a phishing detection method that uses a deep neural network classifier and fuzzy logic to categorize websites into three categories: phishing, non-phishing, and suspicious [18]. Additionally, the Frequent Rule Reduction algorithm (FRR) has created a greedy selection algorithm (GSA) to find the best subset of rules with the most accurate prediction of phishing websites [18].…”

Section: Related Workmentioning

confidence: 99%

“…By combining the best possible set of characteristics and criteria, Kumar and Indrani (2020) proposed a phishing detection method that uses a deep neural network classifier and fuzzy logic to categorize websites into three categories: phishing, non-phishing, and suspicious [18]. Additionally, the Frequent Rule Reduction algorithm (FRR) has created a greedy selection algorithm (GSA) to find the best subset of rules with the most accurate prediction of phishing websites [18]. An artificial neural network-based anti-phishing model for a company has been put up by Sankhwar et al (2020) [19].…”

Section: Related Workmentioning

confidence: 99%

Untitled

2023

J Math Techniques Comput Math

View full text Add to dashboard Cite

Cybercriminals frequently use phishing attempts to trick unwary individuals into disclosing their personal information. The detection of the cybersecurity (CS) state of Internet of Things (IoT) devices determines the necessity to search for and create techniques of detecting various threat types. Thanks to the unification used in the mass manufacture ofIoT devices, it is simpler to make software and hardware modifications in order to prohibit some built-in protection mechanisms from the standpoint of a potential intruder. It becomes vital to offer standard ways of data analysis from both internal and external information sources in order to evaluate the level of device cybersecurity.

show abstract

“…Kumar and Indrani (2020) suggested a phishing detection technique using a deep neural network classifier and fuzzy logic to classify websites into three types, Phishing, Non-Phishing, and Suspicious through the use of the optimum collection of features and rules. Also, a greedy selection algorithm (GSA) has been developed by the Frequent Rule Reduction algorithm (FRR) to detect the best subset of rules that have an efficient prediction of phishing websites [28]. Sankhwar et al (2020) have proposed an antiphishing model for an enterprise using an artificial neural network.…”

Section: Related Workmentioning

confidence: 99%

Detecting Phishing Cyber Attack Based on Fuzzy Rules and Differential Evaluation

Abdul-Hussein¹,

Mohammed²,

Kadhim³

2022

TEM Journal

View full text Add to dashboard Cite

Cyber-criminal attacks witnessed various phishing attacks that blindly attract users to use their secret personal information. This research highlights this type of attack and proposes the development of a new model to detect phishing websites. Two aspects of improvement were followed. Firstly, a new feature is inferred from a combination of features with higher classification capability than the original features. Secondly, a novel method has been proposed by using differential evaluation (DE) to select the best rules among the fuzzy rule set; the DE is a viable way to optimize the fuzzy rule, improving the classification complexity. The proposed system was evaluated by applying two malicious and legitimate datasets collected from Phishtank and Alexa websites. Results show the combination feature can include a promising method for detecting phishing attacks according to the evaluation metrics in the precision of 0.973, recall of 0.933, F-measure of 0.947, and accuracy of 0.976.

show abstract

Frequent rule reduction for phishing URL classification using fuzzy deep neural network model

Cited by 8 publications

References 19 publications

Applications of deep learning for phishing detection: a systematic literature review

Applications of deep learning for phishing detection: a systematic literature review

Untitled

Detecting Phishing Cyber Attack Based on Fuzzy Rules and Differential Evaluation

Contact Info

Product

Resources

About